BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Rome
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261005T104243Z
UID:B8BE34CC-2ACF-41C8-8B8A-C18C280E6D4B
DTSTART;TZID=Europe/Rome:20261013T103000
DTEND;TZID=Europe/Rome:20261013T233000
DESCRIPTION:The unprecedented scale\, heterogeneity\, and performance requi
 rements of future 6G wireless networks are fundamentally challenging tradi
 tional optimization-centric approaches to resource management. These chall
 enges are motivating a paradigm shift toward artificial intelligence (AI)
 –driven wireless optimization and decision-making frameworks. This lectu
 re explores how deep unsupervised learning and generative AI techniques ca
 n be leveraged to solve both convex and non-convex resource allocation pro
 blems under complex nonlinear constraints. Particular emphasis is placed o
 n deep unsupervised learning architectures\, deep implicit layers\, and di
 fferentiable projection methods that enable constraint-aware optimization 
 in applications such as beamforming\, phase-shift optimization\, and power
  allocation. The lecture further examines the emerging role of generative 
 AI models\, including large language models (LLMs)\, in enabling adaptive\
 , scalable\, and environment-aware wireless resource management strategies
  that reduce dependence on frequent model redesign and retraining. The lec
 ture concludes by discussing key open research challenges and outlining a 
 roadmap toward robust\, scalable\, and AI-native wireless intelligence for
  future 6G networks and beyond.\n\nCo-sponsored by: Sapienza University of
  Rome\n\nSpeaker(s): Hina Tabassum\n\nRoom: Sala Lettura 2° piano\, Dipar
 timento di Ingegneria dell'Informazione\, Elettronica e Telecomunicazioni 
 (DIET)\, via Eudossiana 18\, Roma\, Lazio\, Italy\, 00184\, Virtual: https
 ://events.vtools.ieee.org/m/578952
LOCATION:Room: Sala Lettura 2° piano\, Dipartimento di Ingegneria dell'Inf
 ormazione\, Elettronica e Telecomunicazioni (DIET)\, via Eudossiana 18\, R
 oma\, Lazio\, Italy\, 00184\, Virtual: https://events.vtools.ieee.org/m/57
 8952
ORGANIZER:daniele.tarchi@unifi.it
SEQUENCE:12
SUMMARY:Deep Learning and Generative AI for Wireless Networks Resource Mana
 gement
URL;VALUE=URI:https://events.vtools.ieee.org/m/578952
X-ALT-DESC:Description: <br /><p>The unprecedented scale\, heterogeneity\, 
 and performance requirements of future 6G wireless networks are fundamenta
 lly challenging traditional optimization-centric approaches to resource ma
 nagement. These challenges are motivating a paradigm shift toward artifici
 al intelligence (AI)&ndash\;driven wireless optimization and decision-maki
 ng frameworks. This lecture explores how deep unsupervised learning and ge
 nerative AI techniques can be leveraged to solve both convex and non-conve
 x resource allocation problems under complex nonlinear constraints. Partic
 ular emphasis is placed on deep unsupervised learning architectures\, deep
  implicit layers\, and differentiable projection methods that enable const
 raint-aware optimization in applications such as beamforming\, phase-shift
  optimization\, and power allocation. The lecture further examines the eme
 rging role of generative AI models\, including large language models (LLMs
 )\, in enabling adaptive\, scalable\, and environment-aware wireless resou
 rce management strategies that reduce dependence on frequent model redesig
 n and retraining. The lecture concludes by discussing key open research ch
 allenges and outlining a roadmap toward robust\, scalable\, and AI-native 
 wireless intelligence for future 6G networks and beyond.</p>
END:VEVENT
END:VCALENDAR